Remix.run Logo
asib an hour ago

Does anyone have any understanding of how they do this?

My knowledge of how these models work is basically that they are a black box that you put text into and get text out of. I don't phrase it this way to diminish their capability, but more to ask how, other than using a technique like stenography, are they able to hide their true chain of thought in a recoverable way?

rhdunn 40 minutes ago | parent [-]

Welch Labs on YouTube has a great collection of videos on how AI models learn. His recent video [1] covers how image models can learn to encode reasoning in the image processing layers when not given an out of band reasoning set of weights to use instead. I suspect that this applies to LLMs and CoT reasoning vs output token weights.

[1] https://www.youtube.com/watch?v=QgH9sr7G13Q